Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1417 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1272898 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1064813 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.4226. Min Act: -0.0000

Data Index: 491983 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.4356. Min Act: -0.0001

Data Index: 492543 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3788. Min Act: -0.0000

Data Index: 807039 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3746. Min Act: -0.0000

Data Index: 1086631 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3792. Min Act: -0.0000

Data Index: 354337 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3758. Min Act: -0.0000

Data Index: 386300 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3715. Min Act: -0.0000

Data Index: 954219 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3464. Min Act: -0.0000

Data Index: 836858 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3591. Min Act: -0.0000

Data Index: 555199 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3704. Min Act: -0.0000

Data Index: 663297 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3700. Min Act: -0.0000

Data Index: 86672 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3699. Min Act: -0.0000

Data Index: 439446 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3709. Min Act: -0.0000

Data Index: 423145 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3597. Min Act: -0.0000

Data Index: 38460 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3514. Min Act: -0.0000

Data Index: 439479 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3493. Min Act: -0.0000

Data Index: 1222788 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3498. Min Act: -0.0000

Data Index: 823386 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3582. Min Act: -0.0001

Data Index: 961926 (C4 (Web Text))

Max Activating Token Index: 647